Labsco
pixelsoccupied logo

MCP RAN POC

from pixelsoccupied

An MCP server for querying databases and managing Kubernetes clusters.

🔥🔥✓ VerifiedFreeNeeds API keys
#automation#database#devops#security

MCP RAN POC

⚠️ WARNING: THIS IS A PROOF OF CONCEPT (POC) - NOT FOR PRODUCTION USE ⚠️

This repository contains MCP (Model Context Protocol) servers and an ADK agent for database querying and Kubernetes cluster management:

  1. TALM MCP Server - TALM (Topology Aware Lifecycle Manager) interface for Red Hat ACM
  2. PostgreSQL MCP Server - Natural language SQL query interface for PostgreSQL databases
  3. ADK Agent - Google ADK agent providing unified web-based natural language interface to both MCP servers

Architecture Overview

┌─────────────────────┐    ┌─────────────────────┐    ┌─────────────────────┐
│   Web Browser       │    │   Claude Desktop    │    │   Other MCP         │
│   + ADK Agent       │    │      Client         │    │    Clients          │
│     :8000           │    │                     │    │                     │
└─────────┬───────────┘    └─────────┬───────────┘    └─────────┬───────────┘
          │                          │                          │
          └──────────────┬───────────┴────────────┬─────────────┘
                         │                        │
                         ▼                        ▼
          ┌─────────────────────────┐   ┌─────────────────────────────────┐
          │   PostgreSQL MCP        │   │      TALM MCP Server            │
          │     Server :3000        │   │        :3001                    │
          └─────────┬───────────────┘   └─────────┬───────────────────────┘
                    │                             │
                    ▼                             ▼
          ┌─────────────────────────┐   ┌─────────────────────────────────┐
          │   PostgreSQL Database   │   │     Kubernetes Clusters         │
          └─────────────────────────┘   └─────────────────────────────────┘

Local Client Options

cd clients && adk web

Access at http://localhost:8000 for unified natural language interface to both:

  • PostgreSQL database querying and analysis
  • Kubernetes cluster management via TALM

Option 2: Claude Desktop Client

Configure MCP servers in Claude Desktop config:

Configure Claude Desktop Client

Add these configurations to your Claude Desktop config:

TALM Server Configuration

{
 "mcpServers": {
  "talm": {
   "command": "uv",
   "args": [
    "run", 
    "python", "servers/talm.py"
   ],
   "cwd": "/path/to/mcp-ran-poc",
   "env": {
      "KUBECONFIG": "/path/to/your/kubeconfig.yaml"
   }
  }
 }
}

PostgreSQL Server Configuration

{
 "mcpServers": {
  "postgres": {
   "command": "uv",
   "args": [
    "run", 
    "python", "servers/ocloud-pg.py"
   ],
   "cwd": "/path/to/mcp-ran-poc",
   "env": {
      "ALARMS_DB_HOST": "your-postgres-host",
      "ALARMS_DB_PORT": "5432",
      "ALARMS_DB_NAME": "alarms",
      "ALARMS_DB_USER": "alarms",
      "ALARMS_DB_PASSWORD": "your-password",
      "RESOURCES_DB_HOST": "your-postgres-host",
      "RESOURCES_DB_PORT": "5432",
      "RESOURCES_DB_NAME": "resources",
      "RESOURCES_DB_USER": "resources",
      "RESOURCES_DB_PASSWORD": "your-password",
      "CLUSTERS_DB_HOST": "your-postgres-host",
      "CLUSTERS_DB_PORT": "5432",
      "CLUSTERS_DB_NAME": "clusters",
      "CLUSTERS_DB_USER": "clusters",
      "CLUSTERS_DB_PASSWORD": "your-password"
   }
  }
 }
}

Working Configuration Example

This format has been tested and works:

{
 "mcpServers": {
  "talm": {
   "command": "/path/to/uv",
   "args": [
    "run", 
    "--directory", "/path/to/mcp-ran-poc/servers",
    "python", "talm.py"
   ],
   "env": {
      "KUBECONFIG": "/path/to/your/kubeconfig.yaml"
   }
  },
  "postgres": {
   "command": "/path/to/uv",
   "args": [
    "run", 
    "--directory", "/path/to/mcp-ran-poc/servers",
    "python", "ocloud-pg.py"
   ],
   "env": {
    "ALARMS_DB_HOST": "your-postgres-host",
    "ALARMS_DB_PORT": "5432",
    "ALARMS_DB_NAME": "alarms",
    "ALARMS_DB_USER": "alarms",
    "ALARMS_DB_PASSWORD": "your-password",
    "RESOURCES_DB_HOST": "your-postgres-host",
    "RESOURCES_DB_PORT": "5432",
    "RESOURCES_DB_NAME": "resources",
    "RESOURCES_DB_USER": "resources",
    "RESOURCES_DB_PASSWORD": "your-password",
    "CLUSTERS_DB_HOST": "your-postgres-host",
    "CLUSTERS_DB_PORT": "5432",
    "CLUSTERS_DB_NAME": "clusters",
    "CLUSTERS_DB_USER": "clusters",
    "CLUSTERS_DB_PASSWORD": "your-password"
   }
  }
 }
}

Replace:

  • /path/to/mcp-ran-poc with this repository's absolute path
  • /path/to/your/kubeconfig.yaml with your cluster's kubeconfig file
  • your-postgres-host with your PostgreSQL server hostname
  • your-password with your actual database passwords for each database

Server Features

TALM Server

  • Resources: Access to managed clusters, policies, and cluster status
  • Tools: Cluster remediation, health checks, and CGU management
  • Prompts: Guided workflows for cluster lifecycle operations

PostgreSQL Server

  • Tools: execute_query(database, query) - Execute read-only SQL queries safely
  • Security: Only SELECT and WITH queries allowed
  • Response: JSON format with query results, metadata, and executed SQL

ADK Agent

  • Unified Natural Language Interface: Handles both database and cluster operations
  • Database Operations: Convert questions to SQL queries automatically
  • Cluster Operations: Manage Kubernetes clusters via TALM commands
  • Query Explanation: Shows SQL reasoning before execution
  • Result Analysis: Provides insights and analysis of both database and cluster data
  • Schema Exploration: Helps understand database structure and cluster topology
  • Web Interface: User-friendly browser-based interaction at http://localhost:8000
  • Dual MCP Integration: Seamlessly connects to both PostgreSQL and TALM MCP servers